Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint and idempotentHint, and the description reinforces this by saying it 'creates nothing' and 'is always safe to call.' It goes well beyond the annotations by explaining that 'running' means nothing exists yet, that frame and design outputs are only previews/drafts until saved or created, and that booth creation is the one case where something exists afterward.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but dense and front-loaded: purpose, calling convention, polling cadence, and per-status payload meanings each appear in a logical order. Every sentence earns its place because removing any section would lose operational details needed for correct use.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and the annotations cover safety, the description still adds the missing operational picture: time estimates, polling intervals, what each done-state payload means, and the distinction between previews, drafts, and created resources. An agent can call this tool correctly end-to-end based on the description alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema already describes jobId, the description adds important operational meaning: the id must be kept for the conversation, works for 15 minutes even across re-authentication, and omitting it silently falls back to the most recent job. This is exactly the kind of parameter behavior an agent needs to invoke the tool correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Report on background work') and explicitly names the five starting tools it complements. This clearly distinguishes check_generation from all sibling tools such as start_frame or save_frame.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit calling rules: always pass the returned jobId, use the no-argument form only as a recovery fallback, and poll every 15 seconds while waiting. It also tells the agent to wait 10-15 seconds rather than polling tightly and explains what to do with the results, which is actionable guidance an agent can follow without guessing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.